free-coding-models 0.5.70 → 0.5.71

package/README.md

@@ -484,7 +484,7 @@ Then restart Pi. The extension loads automatically. Requires Pi + `free-coding-m
 | `/fcm-router` | Connect Pi to the local FCM Smart Router daemon |
 | `/fcm-status` | Diagnostics: active model, last scan source, daemon state |
 
-**Composite ranking** — SWE-bench (60%) + Latency (20%) + TPS (10%) + Stability (10%). Tiny-context Cerebras models (~8k total tokens) are hidden from Pi/OpenCode pickers since they pass a `hi` probe but fail real agent prompts.
+**Composite ranking** — SWE-bench (60%) + Latency (20%) + TPS (10%) + Stability (10%). Cerebras free-tier models are capped at ~64-65k total tokens (paid tier gets 131k) and are hidden from Pi/OpenCode pickers when they fail real agent prompts.
 
 → Full architecture: [`packages/fcm-pi/README.md`](./packages/fcm-pi/README.md)
 

package/changelog/v0.5.71.md

@@ -0,0 +1,11 @@
+# Changelog v0.5.71 - 2026-08-15
+
+### Fixed
+- **Goose launch wrote a hardcoded 128k context limit** — when launching a model into Goose with `--goose` (or via the TUI Enter flow), the generated `~/.config/goose/custom_providers/fcm-<provider>.json` always set `context_limit: 128000`, ignoring the model's real context window. Models with larger contexts (e.g. MiniMax M3, 1M) were silently capped at 128k, and free-tier models with smaller limits (e.g. Cerebras 64-65k) were advertised above what the API actually allows. The launcher now uses the same `parseContextWindow(model.ctx)` logic as the Install Endpoints flow, so the context limit always matches the catalog value. (Fixes GitHub issue #153)
+- **Stale Cerebras context references in docs** — README.md, packages/fcm-pi/README.md, and the Pi integration docs claimed Cerebras free tier has an "~8k total token limit". Per the official Cerebras Inference docs the free tier now caps context at ~64-65k (paid tier gets 131k). Docs updated to match.
+
+### Changed
+- `parseContextWindow` is now exported from `src/core/endpoint-installer.js` so the Goose launcher (`src/core/tool-launchers.js`) and the Install Endpoints flow share the same single source of truth for context parsing.
+
+### Tests
+- 797/797 tests passing, including a new regression assertion that a 1M-context model launched into Goose produces `context_limit: 1000000` in the generated provider file.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "free-coding-models",
-  "version": "0.5.70",
+  "version": "0.5.71",
   "description": "Find the fastest coding LLM models in seconds — ping free models from multiple providers, pick the best one for OpenCode, Cursor, or any AI coding assistant.",
   "keywords": [
     "nvidia",

package/src/core/endpoint-installer.js

@@ -147,7 +147,7 @@ function getManagedProviderLabel(providerKey) {
   return `FCM ${getProviderLabel(providerKey)}`
 }
 
-function parseContextWindow(ctx) {
+export function parseContextWindow(ctx) {
   if (typeof ctx !== 'string' || !ctx.trim()) return 128000
   const trimmed = ctx.trim().toLowerCase()
   const multiplier = trimmed.endsWith('m') ? 1_000_000 : trimmed.endsWith('k') ? 1_000 : 1

package/src/core/tool-launchers.js

@@ -49,6 +49,7 @@ import { getToolMeta, TOOL_METADATA } from './tool-metadata.js'
 import { PROVIDER_METADATA } from './provider-metadata.js'
 import { resolveToolBinaryPath } from './tool-bootstrap.js'
 import { ensureDir, readJson, writeJson } from './shared-helpers.js'
+import { parseContextWindow } from './endpoint-installer.js'
 
 const OPENAI_COMPAT_ENV_KEYS = [
   'OPENAI_API_KEY',
@@ -338,7 +339,7 @@ function writeGooseConfig(model, apiKey, baseUrl, providerKey, paths = getDefaul
     description: `Managed by free-coding-models for ${providerLabel}`,
     api_key_env: secretEnvName,
     base_url: baseUrl?.endsWith('/chat/completions') ? baseUrl : (baseUrl || ''),
-    models: [{ name: model.modelId, context_limit: 128000 }],
+    models: [{ name: model.modelId, context_limit: parseContextWindow(model.ctx) }],
     supports_streaming: true,
     requires_auth: true,
   }